Convert an existing find-XXXX SKILL.md into a preprocessor Python script, updating config.yaml and removing the old SKILL.md. Covers xref-string-based and LLM_DECOMPILE-based discovery patterns.
Local Python orchestration skill: multi-agent workflows via shared blackboard file, permission gating, token budget scripts, and persistent project context. The bundled Python scripts make no network calls and have zero third-party dependencies. Workflow delegations via the host platform's sessions_send may invoke external model APIs.
Build autonomous AI agents with Claude Agent SDK. TypeScript v0.2.119 | Python v0.1.68.
Use when adding or extending MIDNIGHT DejaVu and Terminal rotation configuration that must stay mirrored across a DejaVu spec plugin and Terminal/terminal/rotation script, especially when the task mentions spec cells, setting cells, macros, cooldown or charge spell registration, brightness or color decoding, or shared Lua/Python rotation behavior.
Analyze data by writing and running Python scripts. Can generate sample data, process CSVs, compute statistics, and create charts.
Orchestrates the generate-review-revise loop using Python critic modules for quality assurance
Development guidelines for DotCraft project. Use this skill when developing DotCraft core features, adding new modules (including external channel adapters via AppServer/JRPC), modifying existing code, or writing documentation. Covers C# code style, tool naming (PascalCase for AI functions), module development norms (via spec), external channel extension with Python SDK, spec-first workflow, testing requirements, and bilingual documentation.
Enforce maintainable, testable, and robust engineering practices for the OpenTulpa codebase. Use when implementing features, refactors, bug fixes, or integrations in this repository, especially for LangGraph runtime, FastAPI routes, Telegram interfaces, scheduler/task flows, and memory/directive behavior. Apply this skill to plan separation-of-concerns changes, preserve runtime behavior, and run repository-specific quality gates and regression checks.
Development guidelines for DotCraft project. Use this skill when developing DotCraft core features, adding new modules (including external channel adapters via AppServer/JRPC), modifying existing code, or writing documentation. Covers C# code style, tool naming (PascalCase for AI functions), module development norms (via spec), external channel extension with Python SDK, spec-first workflow, testing requirements, and bilingual documentation.
Writes Python code following FiftyOne's official conventions. Use when contributing to FiftyOne, developing plugins, or writing code that integrates with FiftyOne's codebase.
Build APIs with Vespera - FastAPI-like DX for Rust/Axum. Covers route handlers, Schema derivation, and OpenAPI generation.
Use when tasks involve browser automation with bridgic-browser via terminal CLI (`bridgic-browser ...`) or Python SDK (`from bridgic.browser.session import Browser`, `from bridgic.browser.tools import BrowserToolSetBuilder`). Trigger for navigation, scraping, form filling, accessibility snapshot refs, e2e checks, stealth browsing, CLI-SDK mapping/migration, and generating SDK code from CLI action steps. --- ## Prerequisite (Important!!) Before performing any operations, **MAKE SURE to use `uv`** to initialize the execution environment and install dependencies first. Note: DO NOT rely on any execution environment other than `uv`, to ensure the execution environment is isolated from the host machine. - **Initialize project**: `[ -f pyproject.toml ] || uv init --bare --python 3.10` - **Install dependencies**: `uv add --upgrade bridgic-browser`. - **Ensure that `uv` is available**: If `uv` is not found or not installed, run `pip install uv` to install it. Then rerun the previous "Install dependencies" step. - **Install browser binaries** (one-time): `uv run playwright install chromium` The CLI tools (`references/cli-guide.md`) and the Python SDK (`references/sdk-guide.md`) come from the **same package** — installing one installs both. ## Strategies & Guidelines (Important!!) When writing browser automation or web scraping code, **ALWAYS follow this "explore first, then coding" strategy**: - First, use the `bridgic-browser` CLI tools to explore the page structure. It is recommended to use headed mode with the command `bridgic-browser open --headed <url>` during exploration. - Then, use the `bridgic-browser` Python SDK to write the code.
skill-sample/ ├─ SKILL.md ⭐ Required: skill entry doc (purpose / usage / examples / deps) ├─ manifest.sample.json ⭐ Recommended: machine-readable metadata (index / validation / autofill) ├─ LICENSE.sample ⭐ Recommended: license & scope (open source / restriction / commercial) ├─ scripts/ │ └─ example-run.py ✅ Runnable example script for quick verification ├─ assets/ │ ├─ example-formatting-guide.md 🧩 Output conventions: layout / structure / style │ └─ example-template.tex 🧩 Templates: quickly generate standardized output └─ references/ 🧩 Knowledge base: methods / guides / best practices ├─ example-ref-structure.md 🧩 Structure reference ├─ example-ref-analysis.md 🧩 Analysis reference └─ example-ref-visuals.md 🧩 Visual reference
More Agent Skills specs Anthropic docs: https://agentskills.io/home
├─ ⭐ Required: YAML Frontmatter (must be at top) │ ├─ ⭐ name : unique skill name, follow naming convention │ └─ ⭐ description : include trigger keywords for matching │ ├─ ✅ Optional: Frontmatter extension fields │ ├─ ✅ license : license identifier │ ├─ ✅ compatibility : runtime constraints when needed │ ├─ ✅ metadata : key-value fields (author/version/source_url...) │ └─ 🧩 allowed-tools : tool whitelist (experimental) │ └─ ✅ Recommended: Markdown body (progressive disclosure) ├─ ✅ Overview / Purpose ├─ ✅ When to use ├─ ✅ Step-by-step ├─ ✅ Inputs / Outputs ├─ ✅ Examples ├─ 🧩 Files & References ├─ 🧩 Edge cases ├─ 🧩 Troubleshooting └─ 🧩 Safety notes
Skill files are scattered across GitHub and communities, difficult to search, and hard to evaluate. SkillWink organizes open-source skills into a searchable, filterable library you can directly download and use.
We provide keyword search, version updates, multi-metric ranking (downloads / likes / comments / updates), and open SKILL.md standards. You can also discuss usage and improvements on skill detail pages.
Quick Start:
Import/download skills (.zip/.skill), then place locally:
~/.claude/skills/ (Claude Code)
~/.codex/skills/ (Codex CLI)
One SKILL.md can be reused across tools.
Everything you need to know: what skills are, how they work, how to find/import them, and how to contribute.
A skill is a reusable capability package, usually including SKILL.md (purpose/IO/how-to) and optional scripts/templates/examples.
Think of it as a plugin playbook + resource bundle for AI assistants/toolchains.
Skills use progressive disclosure: load brief metadata first, load full docs only when needed, then execute by guidance.
This keeps agents lightweight while preserving enough context for complex tasks.
Use these three together:
Note: file size for all methods should be within 10MB.
Typical paths (may vary by local setup):
One SKILL.md can usually be reused across tools.
Yes. Most skills are standardized docs + assets, so they can be reused where format is supported.
Example: retrieval + writing + automation scripts as one workflow.
Some skills come from public GitHub repositories and some are uploaded by SkillWink creators. Always review code before installing and own your security decisions.
Most common reasons:
We try to avoid that. Use ranking + comments to surface better skills:
